Upload folder using huggingface_hub

hubert/general/09_hubert-xlarge-ls960-ft/all_results.json

@@ -0,0 +1,21 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.1816354990005493,
+    "eval_mse_0": 1.4414238929748535,
+    "eval_mse_1": 0.9563913345336914,
+    "eval_mse_2": 0.9795407056808472,
+    "eval_mse_3": 1.3491861820220947,
+    "eval_pcc_0": 0.6698570386130588,
+    "eval_pcc_1": 0.7434186880790876,
+    "eval_pcc_2": 0.7411110360902938,
+    "eval_pcc_3": 0.693096281237125,
+    "eval_runtime": 202.4713,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 12.347,
+    "eval_steps_per_second": 1.546,
+    "train_loss": 1.8317959818977136,
+    "train_runtime": 20415.0173,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.674,
+    "train_steps_per_second": 0.46
+}

hubert/general/09_hubert-xlarge-ls960-ft/args.json

@@ -0,0 +1,11 @@
+{
+    "batch_size": 4,
+    "model_name": "facebook/hubert-xlarge-ls960-ft",
+    "learning_rate": 1e-05,
+    "num_train_epochs": 30,
+    "save_dir": "./model_saved",
+    "freeze_feature_extractor": false,
+    "exp_name": "facebook/hubert-xlarge-ls960-ft_lr1e-05_epochs30_batch4",
+    "save_dir_path": "./model_saved/facebook/hubert-xlarge-ls960-ft_lr1e-05_epochs30_batch4",
+    "save_log_path": "./model_saved/logs/facebook/hubert-xlarge-ls960-ft_lr1e-05_epochs30_batch4"
+}

hubert/general/09_hubert-xlarge-ls960-ft/eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 30.0,
+    "eval_loss": 1.1816354990005493,
+    "eval_mse_0": 1.4414238929748535,
+    "eval_mse_1": 0.9563913345336914,
+    "eval_mse_2": 0.9795407056808472,
+    "eval_mse_3": 1.3491861820220947,
+    "eval_pcc_0": 0.6698570386130588,
+    "eval_pcc_1": 0.7434186880790876,
+    "eval_pcc_2": 0.7411110360902938,
+    "eval_pcc_3": 0.693096281237125,
+    "eval_runtime": 202.4713,
+    "eval_samples": 2500,
+    "eval_samples_per_second": 12.347,
+    "eval_steps_per_second": 1.546
+}

hubert/general/09_hubert-xlarge-ls960-ft/finetuned_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df483e889ecf862845278464c0fec6eae104367452edbb72e9e28e4686790625
+size 3850336162

hubert/general/09_hubert-xlarge-ls960-ft/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f161c8a05033a6f51ba6e0e8309807bd5db8676ebf593db5a428e14946b4d7c5
+size 3850109072

hubert/general/09_hubert-xlarge-ls960-ft/model_weights.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca204cd465cf576f233aabe28d839490ac9a2934b6da9d420d0e019b28774ba5
+size 3850327978

hubert/general/09_hubert-xlarge-ls960-ft/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

hubert/general/09_hubert-xlarge-ls960-ft/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 30.0,
+    "train_loss": 1.8317959818977136,
+    "train_runtime": 20415.0173,
+    "train_samples": 2500,
+    "train_samples_per_second": 3.674,
+    "train_steps_per_second": 0.46
+}

hubert/general/09_hubert-xlarge-ls960-ft/trainer_args.json

@@ -0,0 +1 @@
+{"output_dir": "./model_saved/facebook/hubert-xlarge-ls960-ft_lr1e-05_epochs30_batch4", "overwrite_output_dir": false, "do_train": false, "do_eval": true, "do_predict": false, "evaluation_strategy": "epoch", "prediction_loss_only": false, "per_device_train_batch_size": 4, "per_device_eval_batch_size": 4, "per_gpu_train_batch_size": null, "per_gpu_eval_batch_size": null, "gradient_accumulation_steps": 1, "eval_accumulation_steps": null, "eval_delay": 0, "learning_rate": 1e-05, "weight_decay": 0.0, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1.0, "num_train_epochs": 30, "max_steps": -1, "lr_scheduler_type": "linear", "lr_scheduler_kwargs": {}, "warmup_ratio": 0.0, "warmup_steps": 0, "log_level": "info", "log_level_replica": "warning", "log_on_each_node": true, "logging_dir": "./model_saved/logs/facebook/hubert-xlarge-ls960-ft_lr1e-05_epochs30_batch4", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 500, "logging_nan_inf_filter": true, "save_strategy": "epoch", "save_steps": 500, "save_total_limit": 3, "save_safetensors": true, "save_on_each_node": false, "save_only_model": false, "no_cuda": false, "use_cpu": false, "use_mps_device": false, "seed": 42, "data_seed": null, "jit_mode_eval": false, "use_ipex": false, "bf16": false, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": null, "local_rank": 0, "ddp_backend": null, "tpu_num_cores": null, "tpu_metrics_debug": false, "debug": [], "dataloader_drop_last": false, "eval_steps": null, "dataloader_num_workers": 0, "past_index": -1, "run_name": "./model_saved/facebook/hubert-xlarge-ls960-ft_lr1e-05_epochs30_batch4", "disable_tqdm": false, "remove_unused_columns": true, "label_names": null, "load_best_model_at_end": false, "metric_for_best_model": null, "greater_is_better": null, "ignore_data_skip": false, "fsdp": [], "fsdp_min_num_params": 0, "fsdp_config": {"min_num_params": 0, "xla": false, "xla_fsdp_grad_ckpt": false}, "fsdp_transformer_layer_cls_to_wrap": null, "deepspeed": null, "label_smoothing_factor": 0.0, "optim": "adamw_torch", "optim_args": null, "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": ["tensorboard"], "ddp_find_unused_parameters": null, "ddp_bucket_cap_mb": null, "ddp_broadcast_buffers": null, "dataloader_pin_memory": true, "dataloader_persistent_workers": false, "skip_memory_metrics": true, "use_legacy_prediction_loop": false, "push_to_hub": false, "resume_from_checkpoint": null, "hub_model_id": null, "hub_strategy": "every_save", "hub_token": "<HUB_TOKEN>", "hub_private_repo": false, "hub_always_push": false, "gradient_checkpointing": false, "gradient_checkpointing_kwargs": null, "include_inputs_for_metrics": false, "fp16_backend": "auto", "push_to_hub_model_id": null, "push_to_hub_organization": null, "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": null, "ray_scope": "last", "ddp_timeout": 1800, "torch_compile": false, "torch_compile_backend": null, "torch_compile_mode": null, "dispatch_batches": null, "split_batches": false, "include_tokens_per_second": false, "include_num_input_tokens_seen": false, "neftune_noise_alpha": null}

hubert/general/09_hubert-xlarge-ls960-ft/trainer_state.json

@@ -0,0 +1,618 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "eval_steps": 500,
+  "global_step": 9390,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.140588283538818,
+      "eval_mse_0": 7.435591220855713,
+      "eval_mse_1": 7.100518703460693,
+      "eval_mse_2": 7.136729717254639,
+      "eval_mse_3": 6.88952112197876,
+      "eval_pcc_0": 0.3321853753898314,
+      "eval_pcc_1": 0.1292132452174915,
+      "eval_pcc_2": -0.4273375557626826,
+      "eval_pcc_3": -0.29260647246106986,
+      "eval_runtime": 207.974,
+      "eval_samples_per_second": 12.021,
+      "eval_steps_per_second": 1.505,
+      "step": 313
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.467518636847711e-06,
+      "loss": 17.9531,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.607877016067505,
+      "eval_mse_0": 2.7407641410827637,
+      "eval_mse_1": 2.542466163635254,
+      "eval_mse_2": 2.387968063354492,
+      "eval_mse_3": 2.760310649871826,
+      "eval_pcc_0": 0.3247412204399165,
+      "eval_pcc_1": 0.3855370176479368,
+      "eval_pcc_2": -0.2185190650729273,
+      "eval_pcc_3": -0.39389346086195337,
+      "eval_runtime": 204.8284,
+      "eval_samples_per_second": 12.205,
+      "eval_steps_per_second": 1.528,
+      "step": 626
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.199923515319824,
+      "eval_mse_0": 2.476787567138672,
+      "eval_mse_1": 1.9805853366851807,
+      "eval_mse_2": 1.9669939279556274,
+      "eval_mse_3": 2.3753249645233154,
+      "eval_pcc_0": 0.3508155316343387,
+      "eval_pcc_1": 0.4355783995060166,
+      "eval_pcc_2": 0.4197374892446766,
+      "eval_pcc_3": 0.35837616081397605,
+      "eval_runtime": 201.94,
+      "eval_samples_per_second": 12.38,
+      "eval_steps_per_second": 1.55,
+      "step": 939
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 8.935037273695422e-06,
+      "loss": 2.7266,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4306210279464722,
+      "eval_mse_0": 1.603594183921814,
+      "eval_mse_1": 1.2315700054168701,
+      "eval_mse_2": 1.2911419868469238,
+      "eval_mse_3": 1.59618079662323,
+      "eval_pcc_0": 0.5687736592390981,
+      "eval_pcc_1": 0.6282549499779866,
+      "eval_pcc_2": 0.6121276444655345,
+      "eval_pcc_3": 0.5830968430069369,
+      "eval_runtime": 201.8472,
+      "eval_samples_per_second": 12.386,
+      "eval_steps_per_second": 1.551,
+      "step": 1252
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 8.402555910543132e-06,
+      "loss": 1.3849,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.5424772500991821,
+      "eval_mse_0": 1.799242615699768,
+      "eval_mse_1": 1.3418903350830078,
+      "eval_mse_2": 1.3145965337753296,
+      "eval_mse_3": 1.7141791582107544,
+      "eval_pcc_0": 0.5963398325057564,
+      "eval_pcc_1": 0.6802640081040289,
+      "eval_pcc_2": 0.6649732652449494,
+      "eval_pcc_3": 0.6171472875265727,
+      "eval_runtime": 201.5504,
+      "eval_samples_per_second": 12.404,
+      "eval_steps_per_second": 1.553,
+      "step": 1565
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.382991075515747,
+      "eval_mse_0": 1.6216967105865479,
+      "eval_mse_1": 1.1609082221984863,
+      "eval_mse_2": 1.156604290008545,
+      "eval_mse_3": 1.5927505493164062,
+      "eval_pcc_0": 0.6075793243251464,
+      "eval_pcc_1": 0.6916585567744281,
+      "eval_pcc_2": 0.6768312640525832,
+      "eval_pcc_3": 0.6257270747563107,
+      "eval_runtime": 201.7301,
+      "eval_samples_per_second": 12.393,
+      "eval_steps_per_second": 1.552,
+      "step": 1878
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 7.870074547390843e-06,
+      "loss": 1.1093,
+      "step": 2000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.3673890829086304,
+      "eval_mse_0": 1.5879868268966675,
+      "eval_mse_1": 1.1556898355484009,
+      "eval_mse_2": 1.16941499710083,
+      "eval_mse_3": 1.5564643144607544,
+      "eval_pcc_0": 0.6256968537746085,
+      "eval_pcc_1": 0.6962106651695993,
+      "eval_pcc_2": 0.6802580736327741,
+      "eval_pcc_3": 0.6420275468650636,
+      "eval_runtime": 201.2949,
+      "eval_samples_per_second": 12.42,
+      "eval_steps_per_second": 1.555,
+      "step": 2191
+    },
+    {
+      "epoch": 7.99,
+      "learning_rate": 7.337593184238552e-06,
+      "loss": 0.9985,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.3107062578201294,
+      "eval_mse_0": 1.5334199666976929,
+      "eval_mse_1": 1.0947901010513306,
+      "eval_mse_2": 1.1426668167114258,
+      "eval_mse_3": 1.471946358680725,
+      "eval_pcc_0": 0.635486359916208,
+      "eval_pcc_1": 0.7003068705214422,
+      "eval_pcc_2": 0.6852224662303055,
+      "eval_pcc_3": 0.6528245049811743,
+      "eval_runtime": 201.9436,
+      "eval_samples_per_second": 12.38,
+      "eval_steps_per_second": 1.55,
+      "step": 2504
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.3083852529525757,
+      "eval_mse_0": 1.562683343887329,
+      "eval_mse_1": 1.0696303844451904,
+      "eval_mse_2": 1.1005332469940186,
+      "eval_mse_3": 1.5006946325302124,
+      "eval_pcc_0": 0.6375992541519011,
+      "eval_pcc_1": 0.7136589291767848,
+      "eval_pcc_2": 0.7005731552676023,
+      "eval_pcc_3": 0.6595421646271306,
+      "eval_runtime": 201.9301,
+      "eval_samples_per_second": 12.381,
+      "eval_steps_per_second": 1.55,
+      "step": 2817
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 6.805111821086262e-06,
+      "loss": 0.9287,
+      "step": 3000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.2918624877929688,
+      "eval_mse_0": 1.5178720951080322,
+      "eval_mse_1": 1.0695446729660034,
+      "eval_mse_2": 1.1202644109725952,
+      "eval_mse_3": 1.459771752357483,
+      "eval_pcc_0": 0.6455060410533777,
+      "eval_pcc_1": 0.7139875341117972,
+      "eval_pcc_2": 0.6991072677816944,
+      "eval_pcc_3": 0.6649327323934061,
+      "eval_runtime": 201.4679,
+      "eval_samples_per_second": 12.409,
+      "eval_steps_per_second": 1.554,
+      "step": 3130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.2428473234176636,
+      "eval_mse_0": 1.506658673286438,
+      "eval_mse_1": 0.9951799511909485,
+      "eval_mse_2": 1.038999080657959,
+      "eval_mse_3": 1.430549144744873,
+      "eval_pcc_0": 0.6544391136484241,
+      "eval_pcc_1": 0.7309617276247672,
+      "eval_pcc_2": 0.718638844883276,
+      "eval_pcc_3": 0.6787147381397239,
+      "eval_runtime": 201.8231,
+      "eval_samples_per_second": 12.387,
+      "eval_steps_per_second": 1.551,
+      "step": 3443
+    },
+    {
+      "epoch": 11.18,
+      "learning_rate": 6.272630457933972e-06,
+      "loss": 0.8895,
+      "step": 3500
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 1.2360869646072388,
+      "eval_mse_0": 1.4998555183410645,
+      "eval_mse_1": 0.9904316663742065,
+      "eval_mse_2": 1.024684190750122,
+      "eval_mse_3": 1.4293761253356934,
+      "eval_pcc_0": 0.6570043695967688,
+      "eval_pcc_1": 0.7327004921524575,
+      "eval_pcc_2": 0.7222144796364754,
+      "eval_pcc_3": 0.6793404314476603,
+      "eval_runtime": 201.7084,
+      "eval_samples_per_second": 12.394,
+      "eval_steps_per_second": 1.552,
+      "step": 3756
+    },
+    {
+      "epoch": 12.78,
+      "learning_rate": 5.7401490947816826e-06,
+      "loss": 0.8561,
+      "step": 4000
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 1.186964988708496,
+      "eval_mse_0": 1.4093759059906006,
+      "eval_mse_1": 0.9752281308174133,
+      "eval_mse_2": 1.0252645015716553,
+      "eval_mse_3": 1.3379892110824585,
+      "eval_pcc_0": 0.6610416519496135,
+      "eval_pcc_1": 0.7330282025596999,
+      "eval_pcc_2": 0.7225010109514696,
+      "eval_pcc_3": 0.682869058652847,
+      "eval_runtime": 202.3381,
+      "eval_samples_per_second": 12.356,
+      "eval_steps_per_second": 1.547,
+      "step": 4069
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 1.2552303075790405,
+      "eval_mse_0": 1.517746090888977,
+      "eval_mse_1": 1.0446723699569702,
+      "eval_mse_2": 1.0555921792984009,
+      "eval_mse_3": 1.4029089212417603,
+      "eval_pcc_0": 0.659864670929219,
+      "eval_pcc_1": 0.7313305515043458,
+      "eval_pcc_2": 0.72198097409224,
+      "eval_pcc_3": 0.6827621806416582,
+      "eval_runtime": 201.8081,
+      "eval_samples_per_second": 12.388,
+      "eval_steps_per_second": 1.551,
+      "step": 4382
+    },
+    {
+      "epoch": 14.38,
+      "learning_rate": 5.207667731629393e-06,
+      "loss": 0.8099,
+      "step": 4500
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 1.1650776863098145,
+      "eval_mse_0": 1.3974725008010864,
+      "eval_mse_1": 0.9610859155654907,
+      "eval_mse_2": 0.9950138926506042,
+      "eval_mse_3": 1.306738257408142,
+      "eval_pcc_0": 0.6676793034978875,
+      "eval_pcc_1": 0.7380582882969213,
+      "eval_pcc_2": 0.731019722585482,
+      "eval_pcc_3": 0.6899244344255041,
+      "eval_runtime": 201.7303,
+      "eval_samples_per_second": 12.393,
+      "eval_steps_per_second": 1.552,
+      "step": 4695
+    },
+    {
+      "epoch": 15.97,
+      "learning_rate": 4.675186368477103e-06,
+      "loss": 0.779,
+      "step": 5000
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 1.1586414575576782,
+      "eval_mse_0": 1.397317886352539,
+      "eval_mse_1": 0.9393139481544495,
+      "eval_mse_2": 0.9606934785842896,
+      "eval_mse_3": 1.3372410535812378,
+      "eval_pcc_0": 0.6642818421046413,
+      "eval_pcc_1": 0.7360261819876679,
+      "eval_pcc_2": 0.7311487422239107,
+      "eval_pcc_3": 0.6851328204142834,
+      "eval_runtime": 201.6449,
+      "eval_samples_per_second": 12.398,
+      "eval_steps_per_second": 1.552,
+      "step": 5008
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 1.2570418119430542,
+      "eval_mse_0": 1.4872022867202759,
+      "eval_mse_1": 1.0335379838943481,
+      "eval_mse_2": 1.0864713191986084,
+      "eval_mse_3": 1.4209526777267456,
+      "eval_pcc_0": 0.6604261535748595,
+      "eval_pcc_1": 0.7305563167305369,
+      "eval_pcc_2": 0.7238323073032595,
+      "eval_pcc_3": 0.6821890428657863,
+      "eval_runtime": 201.8903,
+      "eval_samples_per_second": 12.383,
+      "eval_steps_per_second": 1.55,
+      "step": 5321
+    },
+    {
+      "epoch": 17.57,
+      "learning_rate": 4.142705005324814e-06,
+      "loss": 0.7408,
+      "step": 5500
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 1.1428101062774658,
+      "eval_mse_0": 1.3893073797225952,
+      "eval_mse_1": 0.9294054508209229,
+      "eval_mse_2": 0.9531466960906982,
+      "eval_mse_3": 1.299380898475647,
+      "eval_pcc_0": 0.6679088367565303,
+      "eval_pcc_1": 0.7396085985764467,
+      "eval_pcc_2": 0.7342582049452072,
+      "eval_pcc_3": 0.6911363537848471,
+      "eval_runtime": 202.2236,
+      "eval_samples_per_second": 12.363,
+      "eval_steps_per_second": 1.548,
+      "step": 5634
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.1571155786514282,
+      "eval_mse_0": 1.4190118312835693,
+      "eval_mse_1": 0.9280280470848083,
+      "eval_mse_2": 0.9404815435409546,
+      "eval_mse_3": 1.3409417867660522,
+      "eval_pcc_0": 0.6682194019774856,
+      "eval_pcc_1": 0.7427875065273987,
+      "eval_pcc_2": 0.7396501898842275,
+      "eval_pcc_3": 0.6915069389134062,
+      "eval_runtime": 201.8713,
+      "eval_samples_per_second": 12.384,
+      "eval_steps_per_second": 1.55,
+      "step": 5947
+    },
+    {
+      "epoch": 19.17,
+      "learning_rate": 3.6102236421725247e-06,
+      "loss": 0.7238,
+      "step": 6000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 1.206468105316162,
+      "eval_mse_0": 1.4800180196762085,
+      "eval_mse_1": 0.9734672904014587,
+      "eval_mse_2": 0.9799244403839111,
+      "eval_mse_3": 1.392461895942688,
+      "eval_pcc_0": 0.6642466146760475,
+      "eval_pcc_1": 0.7385687900602412,
+      "eval_pcc_2": 0.7352779965642335,
+      "eval_pcc_3": 0.6877323683595673,
+      "eval_runtime": 202.1008,
+      "eval_samples_per_second": 12.37,
+      "eval_steps_per_second": 1.549,
+      "step": 6260
+    },
+    {
+      "epoch": 20.77,
+      "learning_rate": 3.0777422790202343e-06,
+      "loss": 0.7088,
+      "step": 6500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 1.1578402519226074,
+      "eval_mse_0": 1.4351723194122314,
+      "eval_mse_1": 0.9186131954193115,
+      "eval_mse_2": 0.9427530169487,
+      "eval_mse_3": 1.3348236083984375,
+      "eval_pcc_0": 0.6704243370721358,
+      "eval_pcc_1": 0.7440442951441737,
+      "eval_pcc_2": 0.7416496804420745,
+      "eval_pcc_3": 0.6944026816653991,
+      "eval_runtime": 202.3019,
+      "eval_samples_per_second": 12.358,
+      "eval_steps_per_second": 1.547,
+      "step": 6573
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 1.1406444311141968,
+      "eval_mse_0": 1.3962210416793823,
+      "eval_mse_1": 0.9154603481292725,
+      "eval_mse_2": 0.9374591708183289,
+      "eval_mse_3": 1.313438057899475,
+      "eval_pcc_0": 0.6698199386951219,
+      "eval_pcc_1": 0.7439906577681221,
+      "eval_pcc_2": 0.7421330502854281,
+      "eval_pcc_3": 0.6926696946483227,
+      "eval_runtime": 201.9239,
+      "eval_samples_per_second": 12.381,
+      "eval_steps_per_second": 1.55,
+      "step": 6886
+    },
+    {
+      "epoch": 22.36,
+      "learning_rate": 2.5452609158679447e-06,
+      "loss": 0.6773,
+      "step": 7000
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 1.236534595489502,
+      "eval_mse_0": 1.4872865676879883,
+      "eval_mse_1": 1.0111407041549683,
+      "eval_mse_2": 1.0321340560913086,
+      "eval_mse_3": 1.4155772924423218,
+      "eval_pcc_0": 0.664206730216148,
+      "eval_pcc_1": 0.7409240188249102,
+      "eval_pcc_2": 0.7381736886291791,
+      "eval_pcc_3": 0.6878201806305657,
+      "eval_runtime": 202.1337,
+      "eval_samples_per_second": 12.368,
+      "eval_steps_per_second": 1.548,
+      "step": 7199
+    },
+    {
+      "epoch": 23.96,
+      "learning_rate": 2.012779552715655e-06,
+      "loss": 0.6781,
+      "step": 7500
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 1.2183359861373901,
+      "eval_mse_0": 1.4760469198226929,
+      "eval_mse_1": 1.0057872533798218,
+      "eval_mse_2": 1.0079892873764038,
+      "eval_mse_3": 1.3835225105285645,
+      "eval_pcc_0": 0.6658856517760926,
+      "eval_pcc_1": 0.7422045064421295,
+      "eval_pcc_2": 0.7399964547821444,
+      "eval_pcc_3": 0.6894298871215914,
+      "eval_runtime": 202.563,
+      "eval_samples_per_second": 12.342,
+      "eval_steps_per_second": 1.545,
+      "step": 7512
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 1.2287545204162598,
+      "eval_mse_0": 1.4869484901428223,
+      "eval_mse_1": 1.0097808837890625,
+      "eval_mse_2": 1.0284807682037354,
+      "eval_mse_3": 1.3898066282272339,
+      "eval_pcc_0": 0.6673663722997597,
+      "eval_pcc_1": 0.7430301846259794,
+      "eval_pcc_2": 0.7406376417342528,
+      "eval_pcc_3": 0.6905712371514018,
+      "eval_runtime": 202.0584,
+      "eval_samples_per_second": 12.373,
+      "eval_steps_per_second": 1.549,
+      "step": 7825
+    },
+    {
+      "epoch": 25.56,
+      "learning_rate": 1.4802981895633654e-06,
+      "loss": 0.663,
+      "step": 8000
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 1.1360665559768677,
+      "eval_mse_0": 1.3908511400222778,
+      "eval_mse_1": 0.9185400605201721,
+      "eval_mse_2": 0.9356694221496582,
+      "eval_mse_3": 1.2992055416107178,
+      "eval_pcc_0": 0.6734685621022225,
+      "eval_pcc_1": 0.7456723468205457,
+      "eval_pcc_2": 0.743510781109767,
+      "eval_pcc_3": 0.695788389625463,
+      "eval_runtime": 202.3601,
+      "eval_samples_per_second": 12.354,
+      "eval_steps_per_second": 1.547,
+      "step": 8138
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 1.153149127960205,
+      "eval_mse_0": 1.3927490711212158,
+      "eval_mse_1": 0.9418877959251404,
+      "eval_mse_2": 0.9657155275344849,
+      "eval_mse_3": 1.3122459650039673,
+      "eval_pcc_0": 0.6723764296444689,
+      "eval_pcc_1": 0.7447758788793657,
+      "eval_pcc_2": 0.7425123069056755,
+      "eval_pcc_3": 0.6943075369193308,
+      "eval_runtime": 202.2509,
+      "eval_samples_per_second": 12.361,
+      "eval_steps_per_second": 1.548,
+      "step": 8451
+    },
+    {
+      "epoch": 27.16,
+      "learning_rate": 9.478168264110757e-07,
+      "loss": 0.6396,
+      "step": 8500
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 1.1815203428268433,
+      "eval_mse_0": 1.4370988607406616,
+      "eval_mse_1": 0.9570148587226868,
+      "eval_mse_2": 0.978278636932373,
+      "eval_mse_3": 1.3536897897720337,
+      "eval_pcc_0": 0.6696208657851989,
+      "eval_pcc_1": 0.743329571719787,
+      "eval_pcc_2": 0.7409026926778586,
+      "eval_pcc_3": 0.6924000440187518,
+      "eval_runtime": 202.1607,
+      "eval_samples_per_second": 12.366,
+      "eval_steps_per_second": 1.548,
+      "step": 8764
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 4.1533546325878595e-07,
+      "loss": 0.6298,
+      "step": 9000
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 1.210729956626892,
+      "eval_mse_0": 1.4718821048736572,
+      "eval_mse_1": 0.982571005821228,
+      "eval_mse_2": 1.0087800025939941,
+      "eval_mse_3": 1.379689335823059,
+      "eval_pcc_0": 0.6681430768956459,
+      "eval_pcc_1": 0.7426460626581065,
+      "eval_pcc_2": 0.7401369190106432,
+      "eval_pcc_3": 0.6915859603042628,
+      "eval_runtime": 201.8302,
+      "eval_samples_per_second": 12.387,
+      "eval_steps_per_second": 1.551,
+      "step": 9077
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 1.1816354990005493,
+      "eval_mse_0": 1.4414238929748535,
+      "eval_mse_1": 0.9563913345336914,
+      "eval_mse_2": 0.9795407056808472,
+      "eval_mse_3": 1.3491861820220947,
+      "eval_pcc_0": 0.6698570386130588,
+      "eval_pcc_1": 0.7434186880790876,
+      "eval_pcc_2": 0.7411110360902938,
+      "eval_pcc_3": 0.693096281237125,
+      "eval_runtime": 201.7351,
+      "eval_samples_per_second": 12.392,
+      "eval_steps_per_second": 1.552,
+      "step": 9390
+    },
+    {
+      "epoch": 30.0,
+      "step": 9390,
+      "total_flos": 0.0,
+      "train_loss": 1.8317959818977136,
+      "train_runtime": 20415.0173,
+      "train_samples_per_second": 3.674,
+      "train_steps_per_second": 0.46
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

hubert/general/09_hubert-xlarge-ls960-ft/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab61426a66997d47ab593eba70ce5ce9161c52170ed835f3dbb9500162e0ab6
+size 4792